Abstracts

Most events on this list can be tied to a specific page somewhere on the internet.  List entries contain links to such pages through the "Details".   Occasionally events have no such page or the information on it is inadequate.  In such cases I attempt to cobble together a details page myself.



Using Interaction for Simpler and Better Learning
Seminar Series: Machine Learning Seminar Series 2018
Speaker: Sanjoy Dasgupta

Host: Guy Bresler
Host Affiliation: MIT EECS

Date: Wednesday, April 18, 2018
Time: 3 PM
Location: 32-141 Stata Center

Abstract:

In the usual setup of supervised learning, the learner is given a stack of labeled examples and told to fit a classifier to them. It would be quite unnatural for a human to learn in this way, and indeed this model is known to suffer from a variety of fundamental hardness barriers. However, many of these hurdles can be overcome by moving to a setup in which the learner interacts with a human (or other information source) during the learning process.

We will see how interaction makes it possible to:
1. Learn DNF (disjunctive normal form) concepts.
2. Perform machine teaching in situations where the student’s concept class is unknown.
3. Improve the results of unsupervised learning. We will present a generic approach to “interactive structure learning” that, for instance, yields simple interactive algorithms for topic modeling and hierarchical clustering. Along the way, we will present a novel cost function for hierarchical clustering, as well as an efficient algorithm for approximately minimizing this cost.

Bio:

Sanjoy Dasgupta is a Professor in the Department of Computer Science and Engineering at UC San Diego. He works on algorithms for machine learning, with a focus on unsupervised and interactive learning.

Relevant URL:
For more information please contact: Marcia G. Davidson, 617-253-3049, marcia@csail.mit.edu